Pith. sign in

Paper Citation Record · LEDGER

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database

As of 9 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2507.18028.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2507.18028 v1

Coverage vector

measured 48 of 48 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T14:44:15.949789Z

measured 48 of 48 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

48 of 48 outbound references displayed

  • verified exact3
  • verified fuzzy23
  • unresolved19
  • parse uncertain0
  • malformed identifier3
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8a816104-72bc-4aaa-83b1-bc9615b71001 · outbound

This paper cites Is Your LLM Outdated? A Deep Look at Temporal Generalization.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Is Your LLM Outdated? A Deep Look at Temporal Generalization

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.819755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.819755Z digest=sha256:d856e8124357bc62a19ecfbba470eb17f20ca4198bc096745f946bac870fd5b4

Observation c902c66f-c15c-4c50-9564-cba92f2ede08 · outbound

This paper cites Openagi: When llm meets domain experts.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Openagi: When llm meets domain experts

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.530476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.823442Z digest=sha256:eb5b6aced923f05022b811f7f75738d363b9e590cb61e946be3337f81eb8d758

Observation 7abfbd59-062b-490c-97e7-32e70df980b2 · outbound

This paper cites An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.826474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.826474Z digest=sha256:ad1acb2478c59b3317fdd06eb55af783adbebf4e8698989a5fce57fc2585437c

Observation d5f3f4d0-2230-4c7f-ab81-2cd2b312b9ed · outbound

This paper cites Does fine-tuning llms on new knowledge encourage hallucinations? In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 7765–7784, 2024.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Does fine-tuning llms on new knowledge encourage hallucinations? In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 7765–7784, 2024

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.521412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.829591Z digest=sha256:c6a66ea509c00d70b8dad9908046cdded5645a86591714c8ade49010adbf9048

Observation e7cd1575-5d7c-41aa-b751-8620d65a3d8f · outbound

This paper cites Knowledge editing for large language models: A survey.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Knowledge editing for large language models: A survey

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.513167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.832739Z digest=sha256:6fbf3bceb33f3911acca6be38f5384d899ff5bf8ece3e509454316a3979c7e4a

Observation 993a6f9e-5587-4e7f-bd03-236987a7298f · outbound

This paper cites an unresolved cited work.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Unresolved cited work

Reference 6

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:44:16.504065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.835554Z digest=sha256:ec387f4f42af280b43be406ebd9b3239f1d722487b8206aa7dc4d8f4d3a3f964

Observation 21174928-9bb6-4324-b8fd-e1013c6b8b40 · outbound

This paper cites Can We Edit Factual Knowledge by In-Context Learning?.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Can We Edit Factual Knowledge by In-Context Learning?

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.838593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.838593Z digest=sha256:9a5a773d78291ff4db49badb60b38c4c76a366396c548eacb606728af0288822

Observation b9465663-fb62-476a-b364-659c600a07e8 · outbound

This paper cites Andonian, Yonatan Belinkov, and David Bau.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Andonian, Yonatan Belinkov, and David Bau

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.495312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.841541Z digest=sha256:208811eac29fc7c069ac3f376032a92e4554fb7a349b7dbd6ca79bf017ff9c0b

Observation a44091ac-0930-4de4-a857-7d946ebaf7b7 · outbound

This paper cites Locating and editing factual associations in GPT.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Locating and editing factual associations in GPT

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.487431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.844059Z digest=sha256:8ba301e6a8141f4a462abdb64585bd75b815c53e05e084cfb9ac585015c6a230

Observation 17facefb-b798-4414-bca3-90999e1371df · outbound

This paper cites PMET: precise model editing in a transformer.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database PMET: precise model editing in a transformer

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.478473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.846677Z digest=sha256:0067a96526b1d9ea7b4d1974a2fc97c2b5754c1b4b5b637dcc830aa10e15f39c

Observation c9e60fd8-2fe9-4368-b7b5-6f97b3c155dd · outbound

This paper cites Alphaedit: Null-space constrained model editing for language models.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Alphaedit: Null-space constrained model editing for language models

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.470147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.849215Z digest=sha256:f84ff266cff9c27c3f3b4995bd7f8b9dd504546f94000fd98b7ec27c35f72c5e

Observation 5235e1c3-50cc-4c22-8f0c-28c8ad2a015f · outbound

This paper cites Transformer feed-forward layers are key-value memories.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Transformer feed-forward layers are key-value memories

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.852034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.852034Z digest=sha256:7d3903edc8085be76f4c66b9271ee1227e0783180c6c90c23c412ecb4ee57382

Observation e9450391-cbac-42da-91ac-e03d43ae1840 · outbound

This paper cites Reasons and solutions for the decline in model performance after editing.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Reasons and solutions for the decline in model performance after editing

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.460616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.854623Z digest=sha256:661faf425aba753821955fb2ad9fcca10908fc3115b8c0a4292b0a9a64b0dd26

Observation 1bf38d68-a130-460d-a693-55f9036b3305 · outbound

This paper cites Language models are unsupervised multitask learners.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Language models are unsupervised multitask learners

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.857067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.857067Z digest=sha256:ae9ca5bea6c20bffd21b9d3b2d435ead817d4c4f9599dd10dae141f71915f3ed

Observation 72847247-7f7b-44ed-be66-270530dee0b1 · outbound

This paper cites Mesh-Transformer-JAX: Model-Parallel Implementation of Transformer Lan- guage Model with JAX.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Mesh-Transformer-JAX: Model-Parallel Implementation of Transformer Lan- guage Model with JAX

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.444743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.859475Z digest=sha256:2e6827b6c6760a63c7ccd372079384bda1c6d0c9fba1fd5e69cd087fe8bd45c0

Observation c485dd7c-691f-41f2-850f-b495aac432b2 · outbound

This paper cites The Llama 3 Herd of Models.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database The Llama 3 Herd of Models

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.862216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.862216Z digest=sha256:6516b0110d267537df112cbb8079fa7416f1342422d2a10ce6948c81554c3e60

Observation 3913a3bf-6e44-44da-895b-140e6b798573 · outbound

This paper cites MELO: enhancing model editing with neuron- indexed dynamic lora.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database MELO: enhancing model editing with neuron- indexed dynamic lora

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.435481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.864849Z digest=sha256:90c02e33ee6dce5486da3aa70cb446fd1d4964ac8415b5e27d5064f8e6bf343c

Observation 8090a8b2-7268-4225-8ebe-01e7322190a7 · outbound

This paper cites Editing large language models via adaptive gradient guidance.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Editing large language models via adaptive gradient guidance

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.427445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.867393Z digest=sha256:97c3b316075adf8ee383bec639ae7947532a55c6cd34fce6cafd027f42e54b22

Observation 67ca2245-2b6a-476f-a3c3-3e533bf8b2fe · outbound

This paper cites Zero-shot relation extraction via reading comprehension.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Zero-shot relation extraction via reading comprehension

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.419143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.870262Z digest=sha256:4868d9121f7d1851173266362d160799d2bf1d051b8d23d1fbe65bea986efd42

Observation b06897e3-5dfd-4230-8065-0351a1751a58 · outbound

This paper cites Liu, and Matt Gardner.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Liu, and Matt Gardner

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.872632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.872632Z digest=sha256:d57766250d1f490331b4a8f6b7031cc97455c7d61b07c46f48a559d644cf37ad

Observation 92311efd-b73e-4d41-a6bb-858709418b66 · outbound

This paper cites Measuring massive multitask language understanding.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Measuring massive multitask language understanding

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.875115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.875115Z digest=sha256:1f5236188d1284ddf1891b724165080aacb96827c2815421d03b59bd2e5577a2

Observation f40c10cc-0459-4299-bd9d-ea1224a947af · outbound

This paper cites CommonsenseQA: A question answering challenge targeting commonsense knowledge.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database CommonsenseQA: A question answering challenge targeting commonsense knowledge

Reference 22

Resolution
malformed identifier
no resolver link, observed 2026-08-06T14:44:15.877677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.877677Z digest=sha256:4d6250d0018a220783e730e90b91c48f6891f62e4dddd8ef170b4bbe7a80a339

Observation 66feb24e-86c4-48f5-999a-a844151f72ae · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.880287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.880287Z digest=sha256:c312f1e4371cb09021e0e61d890d5b43dbd409fd11c91b4bc586dfe651e0c060

Observation dcf4bb7c-c3cc-4cf6-bdad-20cb6022b8e9 · outbound

This paper cites A surprisingly robust trick for the Winograd schema challenge.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database A surprisingly robust trick for the Winograd schema challenge

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.883067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.883067Z digest=sha256:7df36fbb46f608501a96dde1321182737075d7390aa5729f9bf64c7c7c9b2e8d

Observation 95fe6da2-dece-4a47-9681-419b620b952f · outbound

This paper cites The LAMBADA dataset: Word prediction requiring a broad discourse context.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database The LAMBADA dataset: Word prediction requiring a broad discourse context

Reference 25

Resolution
malformed identifier
doi_truncated, observed 2026-08-06T14:44:16.002460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.885542Z digest=sha256:abf95660491405667f2fdcbd2472753f524b8c4b39584010b6d46f89c88768f7

Observation e549be96-2093-47fa-b992-f8dfa97a81c4 · outbound

This paper cites A framework for few-shot language model evaluation, 07 2024.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database A framework for few-shot language model evaluation, 07 2024

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.405177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.888123Z digest=sha256:2d4e0526bb90030a60bad2fb925dcb44ea2287814815d825e747fa56a6004efc

Observation e2b7cb81-fb9d-453a-8e0a-1649555cd395 · outbound

This paper cites Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.890696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.890696Z digest=sha256:17f2900d02f313b26d8e26edcc1f4d321f135402c46ab1f8776be728fcbf61e9

Observation 514f39f2-ac52-4756-adf7-74036d1ba37a · outbound

This paper cites Should we really edit language models? on the evaluation of edited language models.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Should we really edit language models? on the evaluation of edited language models

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.397220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.894226Z digest=sha256:75ac54f91345a769a7c952c8a4d12478257ce39b4456ed258dd5f8f0bae9bc4a

Observation 28c71581-f95f-42c9-a1ca-56b831f539cd · outbound

This paper cites Editing the mind of giants: An in-depth exploration of pitfalls of knowledge editing in large language models.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Editing the mind of giants: An in-depth exploration of pitfalls of knowledge editing in large language models

Reference 29

Resolution
verified exact
doi, observed 2026-08-06T14:44:15.993107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.897212Z digest=sha256:246acc45d65159055116870d6cbc16c88d60ef8e4f9100c1c14f27e56d6d43c9

Observation 81d5ffcd-75ae-4fed-872c-9f7fb5f1744c · outbound

This paper cites Model editing harms general abilities of large language models: Regularization to the rescue.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Model editing harms general abilities of large language models: Regularization to the rescue

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.389079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.900311Z digest=sha256:80e87af95fa3da4240d83c7cf255947d796ef6a392257439c3bdd5f3dd0be29a

Observation 81649ef4-7c29-45f8-8870-efa40be149c6 · outbound

This paper cites Perturbation- restrained sequential model editing.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Perturbation- restrained sequential model editing

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.380877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.902783Z digest=sha256:24f4e3035f006dab9b457b025bff159cc1b3d4cc1a18c623ce6180a975403f4c

Observation d3d56aea-ac52-4d8d-bd43-c905d13d48af · outbound

This paper cites Editing Factual Knowledge in Language Models.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Editing Factual Knowledge in Language Models

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.905385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.905385Z digest=sha256:e18c1dfa9cf48a0c9407c14bff0d9e795341b681c6792ce9a67fd20b52b58745

Observation 931655b7-0ed6-4a6d-833f-a14475b6ce09 · outbound

This paper cites Fast Model Editing at Scale.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Fast Model Editing at Scale

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.908025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.908025Z digest=sha256:9c8848b0b46b55330cdc927438f8ea5600bba73c31c9a46bab59e688401254a1

Observation bd2ddaa0-5fcf-4b61-b2a0-8d360eaca940 · outbound

This paper cites InstructEdit: Instruction-based Knowledge Editing for Large Language Models.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database InstructEdit: Instruction-based Knowledge Editing for Large Language Models

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.910606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.910606Z digest=sha256:9d0b60cb438ddd52314845a2d511809d36d8cfe6601586d68437c361a6c1daa5

Observation 3d63417a-fa16-4740-8e1b-ffcd8532d01e · outbound

This paper cites Memory-based model editing at scale.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Memory-based model editing at scale

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.372514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.913212Z digest=sha256:5f0ee85eac427e4a0c55da1f1f10efc531eecea13be9a8525e97203a96228af5

Observation 54ed1f67-4141-4adf-b8cd-f41678a00097 · outbound

This paper cites Transformer-Patcher: One Mistake worth One Neuron.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Transformer-Patcher: One Mistake worth One Neuron

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.915901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.915901Z digest=sha256:15334c8d7870e7661731e1e46627ef771e04caa27bbede68df613dbfa4d2dd60

Observation 5a5dea54-23a3-4aba-8e16-b210321cfd1e · outbound

This paper cites Aging with grace: Lifelong model editing with discrete key-value adaptors.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Aging with grace: Lifelong model editing with discrete key-value adaptors

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.364074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.918527Z digest=sha256:8123ed37abc39db8728c7e6f963fbe028b9e5594e943b0a03791bed965932d7b

Observation 59f7d2bf-a53b-45f3-a04e-293a0a37abb3 · outbound

This paper cites Melo: Enhancing model editing with neuron- indexed dynamic lora.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Melo: Enhancing model editing with neuron- indexed dynamic lora

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.354361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.921199Z digest=sha256:41a70f28d2345436cc1dd8dc84d8442b531acdf9b87314b0165680b0248df2d7

Observation 8e4ec8b9-5e09-453b-b4c2-05106ab804a8 · outbound

This paper cites MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modality.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modality

Reference 39

Resolution
verified exact
local_arxiv, observed 2026-08-06T14:44:16.206736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.924076Z digest=sha256:a0f6d09193f00636208e6fd58383543cbcfeb2b56a43f5946b5badac39d1ee10

Observation 0d404b64-57de-486a-8d1a-16091a2338df · outbound

This paper cites Memory-assisted prompt editing to improve GPT-3 after deployment.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Memory-assisted prompt editing to improve GPT-3 after deployment

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.927082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.927082Z digest=sha256:c5025145bb5d9648871fc7559c67139d03e143e2c21f2d1f70f9eb19cd2f6968

Observation 08c26902-fa80-4164-a22a-b38b549179f8 · outbound

This paper cites Can we edit factual knowledge by in-context learning? In The 2023 Conference on Empirical Methods in Natural Language Processing, 2023.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Can we edit factual knowledge by in-context learning? In The 2023 Conference on Empirical Methods in Natural Language Processing, 2023

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.346082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.930672Z digest=sha256:b6be911945da343d0b2e5de6b45036a202c17cd1507654a1cdef7f741e90e0f0

Observation 5e566481-0512-49b8-83ac-c6070826b1ee · outbound

This paper cites MQuAKE: Assessing knowledge editing in language models via multi-hop questions.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database MQuAKE: Assessing knowledge editing in language models via multi-hop questions

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.337590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.933328Z digest=sha256:845ccde700935655306727a6377b83e8f9b47e5d7db9e444a4c7a187b07ea0e7

Observation da5ddd63-2840-4ede-a17b-b720d38caa18 · outbound

This paper cites PokeMQA: Programmable knowledge editing for multi-hop question answering.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database PokeMQA: Programmable knowledge editing for multi-hop question answering

Reference 43

Resolution
malformed identifier
raw_fallback, observed 2026-08-06T14:44:16.329204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.935984Z digest=sha256:ca79972c943876bb80a290754ccb36581de4e2d168d19a7d8e85f8b37ecd0ee7

Observation 1e63d52c-5a4d-4e99-8f01-c376f5fd5bd4 · outbound

This paper cites Retrieval-enhanced knowledge editing in language models for multi-hop question an- swering.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Retrieval-enhanced knowledge editing in language models for multi-hop question an- swering

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-06T14:44:15.938407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:44:15.938407Z digest=sha256:d9838b2862037e046b6aded76b6b8a28be719c907c3aa7630a944050ecf7050f

Observation 435c27a4-709d-471f-89ca-1e71f9d37164 · outbound

This paper cites subject is a.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database subject is a

Reference 45

Resolution
verified exact
doi, observed 2026-08-06T14:44:15.976890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.940886Z digest=sha256:4d0230fb7f5f21e9ce5df9a35627afe953b8f7f707f826599cf0e64f71d69bbb

Observation 6b70f5c0-2176-4e03-bcad-01243ac8ca56 · outbound

This paper cites an unresolved cited work.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database Unresolved cited work

Reference 46

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:44:16.321001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.944310Z digest=sha256:e1ab1dd90b340dda9f3b242395cbd326f38050167d93ac4ebf1aa1bf6bf0b1a8

Observation a22fb999-0867-46ff-bfb8-1760fca40835 · outbound

This paper cites The boxplots are generated from the mean and variance of weight scores, with the center line indicating the mean, boxes showing ±1 standard deviation, and whiskers ±1.5.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database The boxplots are generated from the mean and variance of weight scores, with the center line indicating the mean, boxes showing ±1 standard deviation, and whiskers ±1.5

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.312816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.946913Z digest=sha256:aa54c257ffb865dd0987478562902631c75c8fa1419d8fe9f190cc2c7c53a855

Observation 31761292-cd72-47d0-9070-7bd1b6a74826 · outbound

This paper cites These results confirm that, during inference, residuals unrelated to the edited facts remain inactive, resulting in near-zero weighted scores.

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database These results confirm that, during inference, residuals unrelated to the edited facts remain inactive, resulting in near-zero weighted scores

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:44:16.303439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-06T14:44:15.949789Z digest=sha256:f9e962293be075b20a706f7080d8aea1a6b8656286b89970758660c1bc4a746c

Pith citing papers

No inbound Pith citation observations are available.